speckit.plan

A planning command that sends separate research and design questions to multiple coding assistants at the same time, then combines their results.

In plain words
What is it for?
Use it to research unclear requirements, compare technical options, and produce planning documents such as research and design artifacts.
Why use it?
It reduces waiting when a plan contains several independent unknowns or technology choices.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/github/spec-kit-copilot/speckit.plan
Clone the repo
git clone --depth 1 https://github.com/github/spec-kit-copilot
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00448
Opus 5 $0.00000 $0.00224
Sonnet 5 $0.00000 $0.00090
Haiku 4.5 $0.00000 $0.00045

Measured yesterday against content hash be0e5fca6075, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

speckit.plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

spec-kit-presets/copilot-sub-agents/commands/speckit.plan.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-Agent Delegation

When executing this command, delegate independent work to parallel sub-agents to reduce total execution time.

How to dispatch sub-agents in Copilot:

  • VS Code: Use the runSubagent tool to spawn each sub-agent in an isolated context.
  • CLI: Delegate to a sub-agent process — Copilot CLI automatically manages subsidiary sub-agent execution. You can also target custom agents defined in .github/agents/ or ~/.copilot/agents/.

Phase 0 — Research in Parallel

When generating research tasks for unknowns in Technical Context, dispatch each research topic as a separate sub-agent:

  • For each NEEDS CLARIFICATION item in Technical Context: → Sub-agent: "Research {unknown} for {feature context}. Return: Decision, Rationale, Alternatives considered."

  • For each technology choice needing best-practices review: → Sub-agent: "Find best practices for {tech} in {domain}. Return: recommended patterns, pitfalls, configuration guidance."

Launch all research sub-agents in parallel, then consolidate their results into research.md.

Phase 1 — Design Artifacts

After research.md is complete, generate the design artifacts. Two of them are independent and one depends on their output, so dispatch them in two waves:

Wave 1 (parallel):

  1. Sub-agent: Data Model — "Extract entities from the feature spec and research findings. Generate data-model.md with entity names, fields, relationships, validation rules, and state transitions."
  2. Sub-agent: Interface Contracts — "Define interface contracts for the project based on the spec and research. Generate files under contracts/ documenting exposed interfaces."

Wait for both to complete.

Wave 2 (after Wave 1):

  1. Sub-agent: Quickstart — "Create quickstart.md with integration scenarios and getting-started guidance based on the spec, data model, and contracts." (Requires data-model.md and contracts/ from Wave 1.)

Once all three artifacts exist, proceed to agent context update and constitution re-evaluation.

Read the full file on GitHub · 39 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 39 lines · 0 tokens per session scan A be0e5fca6075

Subscribe to this mod's changes

speckit.plan is a command published in the GitHub repository github/spec-kit-copilot (11 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 448 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.